Regime Shifts: Implications for Dynamic Strategies (corrected)

Regime shifts present significant challenges for investors because they cause performance to depart significantly from the ranges implied by long-term averages of means and covariances. But regime shifts also present opportunities for gain. The authors show how to apply Markov-switching models to forecast regimes in market turbulence, inflation, and economic growth. They found that a dynamic process outperformed static asset allocation in backtests, especially for investors who seek to avoid large losses.Investors have long recognized that economic conditions frequently undergo regime shifts. The economy often oscillates between a steady, low-volatility state characterized by economic growth and a panic-driven, high-volatility state characterized by economic contraction. These regime shifts present significant challenges for risk management and portfolio construction. Many authors have used Markov-switching models to “fit” a dataset and uncover evidence of regimes in sample, but far fewer authors have attempted out-of-sample forecasting. The goal of our research was to build regime-dependent investment strategies and backtest their performance out of sample. In contrast to previous studies, we did not model regimes directly on asset returns nor did we rely on a specific asset-pricing model. Instead, we forecasted regimes in the important drivers of asset returns and then reallocated assets accordingly.When dealing with regime shifts, we expect Markov-switching models to perform better than simple data partitions based on thresholds. Arbitrary thresholds give false signals because they fail to capture the persistence in regimes and changing volatilities. Markov-switching models are designed to capture these features of the data. We built a simple Markov-switching model to identify and forecast regimes characterized by market turbulence, inflation, and economic growth. Our results revealed the presence of a “normal” and an “event” regime in each series. The event regimes are characterized by more challenging investment conditions, on average, and by greater volatility in those conditions. Both the normal and event regimes exhibited meaningful persistence.Next, we turned to out-of-sample forecasting and backtesting. First, we tested the performance of the regime-switching approach for tactical asset allocation. We used regime forecasts to scale exposure to specific risk premiums over time and found that a dynamic process outperformed constant exposures. We then applied the same methodology to dynamic asset allocation across stocks, bonds, and cash. Again, we found that a dynamic process outperformed static asset allocation, especially for investors who seek to avoid large losses.Authors’ Note: Sébastien Page, CFA, worked on this article while at State Street Global Markets.